{"total":110,"rows":[{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87,"area":null},{"id":"2102.03896","title":"Consequences of Misaligned AI","created":"2021-02-07","cited_by_count":80,"area":null},{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2204.05186","title":"Correcting Robot Plans with Natural Language Feedback","created":"2022-04-11","cited_by_count":69,"area":null},{"id":"2202.00914","title":"Lipschitz-constrained Unsupervised Skill Discovery","created":"2022-02-02","cited_by_count":62,"area":null},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50,"area":null},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35,"area":null},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2106.14305","title":"Unsupervised Skill Discovery with Bottleneck Option Learning","created":"2021-06-27","cited_by_count":28,"area":null},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26,"area":null},{"id":"2107.01969","title":"The MineRL BASALT Competition on Learning from Human Feedback","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2408.05804","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","created":"2024-08-11","cited_by_count":23,"area":null},{"id":"2109.00127","title":"Cognitive science as a source of forward and inverse models of human decisions for robotics and control","created":"2021-09-01","cited_by_count":22,"area":null},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2405.07162","title":"Learning Reward for Robot Skills Using Large Language Models via Self-Alignment","created":"2024-05-12","cited_by_count":20,"area":null},{"id":"2509.01063","title":"An Economy of AI Agents","created":"2025-09-01","cited_by_count":18,"area":null},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2106.01404","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2309.00711","title":"Learning Shared Safety Constraints from Multi-task Demonstrations","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2111.05251","title":"Learning Perceptual Concepts by Bootstrapping from Human Queries","created":"2021-11-09","cited_by_count":12,"area":null},{"id":"2201.02185","title":"Admissible Policy Teaching through Reward Design","created":"2022-01-06","cited_by_count":12,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2210.09378","title":"Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation","created":"2022-10-17","cited_by_count":8,"area":null},{"id":"2301.10095","title":"Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards","created":"2023-01-24","cited_by_count":8,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2312.08884","title":"Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems","created":"2023-12-14","cited_by_count":8,"area":null},{"id":"2409.08212","title":"Adaptive Language-Guided Abstraction from Contrastive Explanations","created":"2024-09-12","cited_by_count":8,"area":null},{"id":"2502.11918","title":"VLP: Vision-Language Preference Learning for Embodied Manipulation","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2103.12142","title":"Combining Reward Information from Multiple Sources","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2109.06689","title":"Reactive and Safe Road User Simulations using Neural Barrier Certificates","created":"2021-09-14","cited_by_count":7,"area":null},{"id":"2205.10316","title":"Complex behavior from intrinsic motivation to occupy action-state path space","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2104.12582","title":"Understanding and Avoiding AI Failures: A Practical Guide","created":"2021-04-22","cited_by_count":6,"area":null},{"id":"2106.07814","title":"Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2108.12820","title":"A Hybrid Rule-Based and Data-Driven Approach to Driver Modeling through Particle Filtering","created":"2021-08-29","cited_by_count":6,"area":null},{"id":"2204.05091","title":"Linguistic communication as (inverse) reward design","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2209.15166","title":"Reward Shaping for User Satisfaction in a REINFORCE Recommender","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2210.07636","title":"Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2106.08272","title":"Deep Reinforcement Learning for Conservation Decisions","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2111.09884","title":"Assisted Robust Reward Design","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2602.06625","title":"FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2105.03052","title":"Informational Design of Dynamic Multi-Agent System","created":"2021-05-07","cited_by_count":4,"area":null},{"id":"2210.15096","title":"Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2402.08062","title":"Avoiding Catastrophe in Online Learning by Asking for Help","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2412.14741","title":"Active Inference and Human--Computer Interaction","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2102.06808","title":"Planning and Learning Using Adaptive Entropy Tree Search","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2202.13985","title":"The dangers in algorithms learning humans' values and irrationalities","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2204.13963","title":"Tailored Uncertainty Estimation for Deep Learning Systems","created":"2022-04-29","cited_by_count":3,"area":null},{"id":"2302.09248","title":"Machine Love","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2408.13567","title":"Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2501.01367","title":"Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2501.15618","title":"Your Learned Constraint is Secretly a Backward Reachable Tube","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2508.16090","title":"GPLight+: A Genetic Programming Method for Learning Symmetric Traffic Signal Control Policy","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2509.10656","title":"Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2102.07017","title":"Mitigating Negative Side Effects via Environment Shaping","created":"2021-02-13","cited_by_count":2,"area":null},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2504.17404","title":"Super Co-alignment of Human and AI for Sustainable Symbiotic Society","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2102.07152","title":"On the Equilibrium Elicitation of Markov Games Through Information Design","created":"2021-02-14","cited_by_count":1,"area":null},{"id":"2107.02912","title":"Supervised Bayesian Specification Inference from Demonstrations","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2302.00813","title":"Goal Alignment: A Human-Aware Account of Value Alignment Problem","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2502.03717","title":"Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2502.14043","title":"Safe Learning Under Irreversible Dynamics via Asking for Help","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2504.15125","title":"Contemplative Artificial Intelligence","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2509.07445","title":"Text2Touch: Tactile In-Hand Manipulation with LLM-Designed Reward Functions","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2601.08869","title":"AI Deployment Authorisation: A Global Standard for Machine-Readable Governance of High-Risk Artificial Intelligence","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2602.01699","title":"Mitigating loss of control in advanced AI systems through instrumental goal trajectories","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.28056","title":"RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2606.08267","title":"Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2103.11782","title":"Reinforcement Learning Assisted Beamforming for Inter-cell Interference Mitigation in 5G Massive MIMO Networks","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2109.00414","title":"Balancing Performance and Human Autonomy with Implicit Guidance Agent","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2109.02332","title":"Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning","created":"2021-09-06","cited_by_count":0,"area":null},{"id":"2112.15034","title":"Self Reward Design with Fine-grained Interpretability","created":"2021-12-30","cited_by_count":0,"area":null},{"id":"2304.03081","title":"Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2310.05871","title":"Dynamic value alignment through preference aggregation of multiple objectives","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2312.07579","title":"Cross Fertilizing Empathy from Brain to Machine as a Value Alignment Strategy","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2402.09734","title":"Agents Need Not Know Their Purpose","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2403.15826","title":"Scaling Learning based Policy Optimization for Temporal Logic Tasks by Controller Network Dropout","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.15514","title":"Superhuman Game AI Disclosure: Expertise and Context Moderate Effects on Trust and Fairness","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2507.03870","title":"Uncovering Systemic and Environment Errors in Autonomous Systems Using Differential Testing","created":"2025-07-05","cited_by_count":0,"area":null}],"next_cursor":"100"}